MULTI-STRATEGY IMPROVED TUNA SWARM OPTIMIZATION (TSO)-BASED HYBRID KERNEL EXTREME LEARNING MACHINE MODEL FOR EARLY DIAGNOSIS OF PARKINSON’S DISEASE

Abstract

Parkinson’s disease (PD) is a neurodegenerative disease that progresses slowly. In this study, a tuna swarm optimization (TSO)-based hybrid kernel extreme learning machine (HKELM) method was proposed for early phonetic recognition of PD. Herein, HKELM models were optimized using multi-strategy (reverse learning and greedy selection swarm initialization, sin–cos strategy disturbance, and Weibull variation disturbance) improved TSO for early diagnosis of PD. The HKELM was employed for early diagnosis of PD and its classification accuracy was evaluated. The results of the experiments reveal that, as compared to the unimproved tuna technique for optimizing ELM, the suggested algorithm converges faster, can leap out of the local optimal, and has higher optimization accuracy.